Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only cover the safety triad, so the description carries the real burden and delivers: it discloses the authenticated native buyer identity and the requirement for an existing funded placement, and the version-scoped wording signals optimistic concurrency (the schema confirms 409 on stale versions). It does not describe what happens on partial success or the returned policy version, keeping it short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, mutation and its precondition front-loaded, no filler. It is efficient, though the second sentence is a prerequisite note rather than strictly necessary framing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-parameter mutation with a fully documented schema and no output schema, the description covers the identity/auth context, the funding prerequisite, and the version-concurrency model an agent needs to avoid a 409. Missing only the post-update state (what the new version becomes).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, including weight semantics (normalize at serving, zero disables), creative_id and expected_version with the stale-update 409 behavior. The description adds only the framing phrase 'expected policy version' and does not extend any parameter meaning, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Replace native creative weights') plus the concurrency frame ('at the expected policy version'), which distinguishes it from siblings like create_creative_experiment, register_creative_variants and get_creative_experiment. It stops short of naming a sibling alternative, but the operation is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Prerequisites are implied rather than spelled out: it names the 'authenticated native buyer' and 'existing funded placement' context, which tells the agent what must already exist. There is no explicit when-to-use vs when-not or pointer to an alternative (e.g. stop_creative_experiment), so usage remains inferred.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.